PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy
Large language models (LLMs) exhibit sycophancy, a tendency to agree with user beliefs regardless of factual accuracy. This can reinforce misconceptions, but eliminating it entirely risks over-correction against valid opinions. Effective control must therefore both reduce and increase sycophancy with predictable and gradual effect. Yet, existing methods fail to ensure a bidirectional and monotonic relationship between steering strength and behavioral outcome across models and datasets. We introduce PCA-guided Activation Scaling (PAS), an activation steering framework that decomposes residual s
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%lllyasviel/ControlNet-v1-1 →
“Fuzzy title match (0.94): “PCA-guided Activation Scaling for Monotonic Bidirectional Co” ≈ “lllyasviel/ControlNet-v1-1””
- FuzzySimilar title/name (fuzzy) · 87%lllyasviel/ControlNet →
“Fuzzy title match (0.94): “PCA-guided Activation Scaling for Monotonic Bidirectional Co” ≈ “lllyasviel/ControlNet””
- FuzzySimilar title/name (fuzzy) · 59%builderz-labs/mission-control →
“Fuzzy title match (0.73): “PCA-guided Activation Scaling for Monotonic Bidirectional Co” ≈ “builderz-labs/mission-control””
- LinkedLinked via arxiv author · 85%Wenzheng Chen →
“PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy”
- LinkedLinked via arxiv author · 85%Zhaoxin Feng →
“PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy”
- LinkedLinked via arxiv author · 85%Yip Tin Po →
“PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy”
- LinkedLinked via arxiv author · 85%Jianfei Ma →
“PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy”
- LinkedLinked via arxiv author · 85%Emmanuele Chersoni →
“PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy”